Related papers: Difference-aware Knowledge Selection for Knowledge…
In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker's emotion. Besides, external commonsense knowledge has been applied…
Existing knowledge-grounded dialogue systems typically use finetuned versions of a pretrained language model (LM) and large-scale knowledge bases. These models typically fail to generalize on topics outside of the knowledge base, and…
A limitation of current neural dialog models is that they tend to suffer from a lack of specificity and informativeness in generated responses, primarily due to dependence on training data that covers a limited variety of scenarios and…
In previous research, knowledge-selection tasks mostly rely on language model-based methods or knowledge ranking. However, while approaches that rely on the language models take all knowledge as sequential input, knowledge does not contain…
Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…
Knowledge Graphs (KGs) have emerged as invaluable resources for enriching recommendation systems by providing a wealth of factual information and capturing semantic relationships among items. Leveraging KGs can significantly enhance…
Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency…
Answer selection, which is involved in many natural language processing applications such as dialog systems and question answering (QA), is an important yet challenging task in practice, since conventional methods typically suffer from the…
Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network. Previous methods mostly focus on proposing feature transformation and loss…
Document-grounded dialogue (DGD) uses documents as external knowledge for dialogue generation. Correctly understanding the dialogue context is crucial for selecting knowledge from the document and generating proper responses. In this paper,…
People speak at different levels of specificity in different situations. Depending on their knowledge, interlocutors, mood, etc.} A conversational agent should have this ability and know when to be specific and when to be general. We…
Despite its breakthrough in classification problems, Knowledge distillation (KD) to recommendation models and ranking problems has not been studied well in the previous literature. This dissertation is devoted to developing knowledge…
In Conversational Recommendation System (CRS), an agent is asked to recommend a set of items to users within natural language conversations. To address the need for both conversational capability and personalized recommendations, prior…
With the rapid development of artificial intelligence technology, especially the increasingly widespread application of question-and-answer systems, high-quality question generation has become a key component in supporting the development…
While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to…
Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods…
Existing knowledge-grounded conversation systems generate responses typically in a retrieve-then-generate manner. They require a large knowledge base and a strong knowledge retrieval component, which is time- and resource-consuming. In this…
Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate…
Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text, raising concerns about their reliability. Previous methods use external knowledge as references for text generation to…
In knowledge grounded conversation, domain knowledge plays an important role in a special domain such as Music. The response of knowledge grounded conversation might contain multiple answer entities or no entity at all. Although existing…